Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Initials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +h
    -0.06
    +m
    -0.06
     ",");↵
    -0.06
     landlords
    -0.06
     letzten
    -0.06
     ','
    -0.06
    楼上
    -0.06
    mscorlib
    -0.06
     연
    -0.06
     Death
    -0.06
    POSITIVE LOGITS
    详见
    0.09
    ewnętrzn
    0.07
     approximately
    0.07
     [[
    0.07
     Hull
    0.06
    olem
    0.06
    Regarding
    0.06
    严密
    0.06
    XMLLoader
    0.06
    挚
    0.06
    Act Density 0.013%

    No Known Activations